MPHGCL-DDI: Meta-Path-Based Heterogeneous Graph Contrastive Learning for Drug-Drug Interaction Prediction
Molecules · 24.05.2024 · 29 (11) · 2483
DOI: 10.3390/molecules29112483 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecules, online erschienen am 24.05.2024. Verfasst von Baofang Hu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Data and Computer Science, Shandong Women's University, Jinan 250030, China. Hauptthemen laut MEDLINE: Drug Interactions. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Natural Science Foundation, China Ministry of Education Industry–Academia Collaboration Collaborative Education Project, Shandong Women’s University High-level Talent Introduction Research Project.
Abstract (Originalsprache)
The combinatorial therapy with multiple drugs may lead to unexpected drug-drug interactions (DDIs) and result in adverse reactions to patients. Predicting DDI events can mitigate the potential risks of combinatorial therapy and enhance drug safety. In recent years, deep models based on heterogeneous graph representation learning have attracted widespread interest in DDI event prediction and have yielded satisfactory results, but there is still room for improvement in prediction performance. In this study, we proposed a meta-path-based heterogeneous graph contrastive learning model, MPHGCL-DDI, for DDI event prediction. The model constructs two contrastive views based on meta-paths: an average graph view and an augmented graph view. The former represents that there are connections between drugs, while the latter reveals how the drugs connect with each other. We defined three levels of data augmentation schemes in the augmented graph view and adopted a combination of three losses in the model training phase: multi-relation prediction loss, unsupervised contrastive loss and supervised contrastive loss. Furthermore, the model incorporates indirect drug information, protein–protein interactions (PPIs), to reveal latent relations of drugs. We evaluated MPHGCL-DDI on three different tasks of two datasets. Experimental results demonstrate that MPHGCL-DDI surpasses several state-of-the-art methods in performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Data and Computer Science, Shandong Women's University, Jinan 250030, China.
- School of Information Science and Engineering, University of Jinan, Jinan 250024, China.
ORCID-Profile: Baofang Hu
Förderung
- Shandong Natural Science Foundation
- China Ministry of Education Industry–Academia Collaboration Collaborative Education Project
- Shandong Women’s University High-level Talent Introduction Research Project
Zitieren
APA
Hu, B., Yu, Z., & Li, M. (2024). MPHGCL-DDI: Meta-Path-Based Heterogeneous Graph Contrastive Learning for Drug-Drug Interaction Prediction. Molecules, 29(11), 2483. https://doi.org/10.3390/molecules29112483
Vancouver
Hu B, Yu Z, Li M. MPHGCL-DDI: Meta-Path-Based Heterogeneous Graph Contrastive Learning for Drug-Drug Interaction Prediction. Molecules. 2024;29(11):2483. doi:10.3390/molecules29112483
BibTeX
@article{Hu2024,
author = {Hu, Baofang and Yu, Zhenmei and Li, Mingke},
title = {MPHGCL-DDI: Meta-Path-Based Heterogeneous Graph Contrastive Learning for Drug-Drug Interaction Prediction},
journal = {Molecules},
year = {2024},
volume = {29},
number = {11},
pages = {2483},
doi = {10.3390/molecules29112483}
}
EUVIMED